With the Text Link Analysis (TLA) node, the extraction of text link analysis pattern results is automatically enabled. In the node's properties, the expert options include certain additional parameters that impact how text is extracted and handled. The expert parameters control the basic behavior, as well as a few advanced behaviors, of the extraction process. There are also a number of linguistic resources and options that also impact the extraction results, which are controlled by the resource template you select.

Limit extraction to concepts with a global frequency of at least [n]. This option specifies the minimum number of times a word or phrase must occur in the text in order for it to be extracted. In this way, a value of 5 limits the extraction to those words or phrases that occur at least five times in the entire set of records or documents.

In some cases, changing this limit can make a big difference in the resulting extraction results, and consequently, your categories. Let's say that you're working with some restaurant data and you don't increase the limit beyond 1 for this option. In this case, you might find pizza (1), thin pizza (2), spinach pizza (2), and favorite pizza (2) in your extraction results. However, if you were to limit the extraction to a global frequency of 5 or more and re-extract, you would no longer get three of these concepts. Instead you would get pizza (7), since pizza is the simplest form and this word already existed as a possible candidate. And depending on the rest of your text, you might actually have a frequency of more than seven, depending on whether there are still other phrases with pizza in the text. Additionally, if spinach pizza was already a category descriptor, you might need to add pizza as a descriptor instead to capture all of the records. For this reason, change this limit with care whenever categories have already been created.

Note that this is an extraction-only feature; if your template contains terms (they usually do), and a term for the template is found in the text, then the term will be indexed regardless of its frequency.

For example, suppose you use a Basic Resources template that includes "los angeles" under the <Location> type in the Core library; if your document contains Los Angeles only once, then Los Angeles will be part of the list of concepts. To prevent this, you'll need to set a filter to display concepts occurring at least the same number of times as the value entered in the Limit extraction to concepts with a global frequency of at least [n] field.

Accommodate punctuation errors. This option temporarily normalizes text containing punctuation errors (for example, improper usage) during extraction to improve the extractability of concepts. This option is extremely useful when text is short and of poor quality (as, for example, in open-ended survey responses, e-mail, and CRM data), or when the text contains many abbreviations.

Accommodate spelling for a minimum word character length of [n]. This option applies a fuzzy grouping technique that helps group commonly misspelled words or closely spelled words under one concept. The fuzzy grouping algorithm temporarily strips all vowels (except the first one) and strips double/triple consonants from extracted words and then compares them to see if they're the same so that modeling and modelling would be grouped together. However, if each term is assigned to a different type, excluding the <Unknown> type, the fuzzy grouping technique won't be applied.

You can also define the minimum number of root characters required before fuzzy grouping is used. The number of root characters in a term is calculated by totaling all of the characters and subtracting any characters that form inflection suffixes and, in the case of compound-word terms, determiners and prepositions. For example, the term exercises is counted as 8 root characters in the form "exercise," since the letter s at the end of the word is an inflection (plural form). Similarly, apple sauce counts as 10 root characters ("apple sauce") and manufacturing of cars counts as 16 root characters (“manufacturing car”). This method of counting is only used to check whether the fuzzy grouping should be applied but doesn't influence how the words are matched.

Extract uniterms. This option extracts single words (uniterms) as long as the word isn't already part of a compound word and if it's either a noun or an unrecognized part of speech.

Extract nonlinguistic entities. This option extracts nonlinguistic entities, such as phone numbers, social security numbers, times, dates, currencies, digits, percentages, e-mail addresses, and HTTP addresses. You can include or exclude certain types of nonlinguistic entities in the Nonlinguistic Entities: Configuration section under the Advanced Resources properties. By disabling any unnecessary entities, the extraction engine won't waste processing time.

Uppercase algorithm. This option extracts simple and compound terms that aren't in the built-in dictionaries as long as the first letter of the term is in uppercase. This option offers a good way to extract most proper nouns.

Group partial and full person names together when possible. This option groups names that appear differently in the text together. This feature is helpful since names are often referred to in their full form at the beginning of the text and then only by a shorter version. This option attempts to match any uniterm with the <Unknown> type to the last word of any of the compound terms that is typed as <Person>. For example, if doe is found and initially typed as <Unknown>, the extraction engine checks to see if any compound terms in the <Person> type include doe as the last word, such as john doe. This option doesn't apply to first names since most are never extracted as uniterms.

Maximum nonfunction word permutation. This option specifies the maximum number of nonfunction words that can be present when applying the permutation technique. This permutation technique groups similar phrases that differ from each other only by the nonfunction words (for example, of and the) contained, regardless of inflection. For example, let's say that you set this value to—at most—two words, and both company officials and officials of the company were extracted. In this case, both extracted terms would be grouped together in the final concept list since both terms are deemed to be the same when of the is ignored.

Use derivation when grouping multiterms. When processing Big Data, select this option to group multiterms by using derivation rules.